SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks – NLPIR自然语言处理与信息检索共享平台

自然语言处理与信息检索共享平台 自然语言处理与信息检索共享平台

SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks

NLPIR SEMINAR Y2019#7

INTRO

In the new semester, our Lab, Web Search Mining and Security Lab, plans to hold an academic seminar every Monday, and each time a keynote speaker will share understanding of papers on his/her related research with you.

Arrangement

This week’s seminar is organized as follows:

  1. The seminar time is 1.pm, Mon, at Zhongguancun Technology Park ,Building 5, 1306.
  2. The lecturer is Ziyu Liu, the paper’s title is SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks.
  3. The seminar will be hosted by Li Shen.
  4. Attachment is the paper of this seminar, please download in advance.

Everyone interested in this topic is welcomed to join us. the following is the abstract for this week’s paper.

SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks

Ke Wang, XiaojunWan

Abstract

       Generating texts of different sentiment labels is getting more and more attention in the area of natural language generation. Recently, Generative Adversarial Net (GAN) has shown promising results in text generation. However, the texts generated by GAN usually suffer from the problems of poor quality, lack of diversity and mode collapse. In this paper, we propose a novel framework – SentiGAN, which has multiple generators and one multi-class discriminator, to address the above problems. In our framework, multiple generators are trained simultaneously, aiming at generating texts of different sentiment labels without supervision. We propose a penalty based objective in the generators to force each of them to generate diversified examples of a specific sentiment label. Moreover, the use of multiple generators and one multi-class discriminator can make each generator focus on generating its own examples of a specific sentiment label accurately. Experimental results on four datasets demonstrate that our model consistently outperforms several state-of-the-art text generation methods in the sentiment accuracy and quality of generated texts.

You May Also Like

About the Author: nlpvv

发表评论